Research on time series prediction model for multi-factor environmental parameters in facilities based on LSTM-AT-DP model

IntroductionExisting facility environment prediction models often suffer from low accuracy, poor timeliness, and error accumulation in long-term predictions under multifactor nonlinear coupling conditions. These limitations significantly constrain the effectiveness of precise environmental regulatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Longwei Liang, Hui Shi, Zhaoyuan Wang, Shengjie Wang, Changhong Li, Ming Diao
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2025.1652478/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330958040301568
author Longwei Liang
Longwei Liang
Hui Shi
Hui Shi
Zhaoyuan Wang
Shengjie Wang
Changhong Li
Ming Diao
author_facet Longwei Liang
Longwei Liang
Hui Shi
Hui Shi
Zhaoyuan Wang
Shengjie Wang
Changhong Li
Ming Diao
author_sort Longwei Liang
collection DOAJ
description IntroductionExisting facility environment prediction models often suffer from low accuracy, poor timeliness, and error accumulation in long-term predictions under multifactor nonlinear coupling conditions. These limitations significantly constrain the effectiveness of precise environmental regulation in agricultural facilities.MethodsTo address these challenges, this paper proposes a novel facility environment prediction model (LSTM-AT-DP) integrating Long Short-Term Memory networks with attention mechanisms and advanced data preprocessing. The model architecture employs: (1) a Data Preprocessing (DP) module combining Wavelet Threshold Denoising (WTD) for noise elimination and Sliding Window (SW) technique for feature matrix construction; (2) an LSTM core for deep temporal modeling; and (3) an Attention Mechanism (AT) for dynamic feature weighting to enhance critical temporal feature extraction.ResultsIn 24-hour prediction tests, the model achieved determination coefficients (R²) of 0.9602 (temperature), 0.9529 (humidity), and 0.9839 (radiation), representing improvements of 3.89%, 5.53%, and 2.84% respectively over baseline LSTM models. Corresponding RMSE reductions were 0.6830, 1.8759, and 12.952 for these parameters.DiscussionThe results demonstrate that the LSTM-AT-DP model significantly enhances prediction accuracy while effectively suppressing error accumulation in long-term forecasts. This advancement provides robust technical support for precise facility environment regulation, with particular improvements observed in humidity prediction. The integrated attention mechanism proves particularly effective in identifying and weighting critical temporal features across all measured environmental parameters.
format Article
id doaj-art-7f818249a31a4e28a4e80aa84e5a9348
institution Kabale University
issn 1664-462X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-7f818249a31a4e28a4e80aa84e5a93482025-08-20T03:46:46ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2025-08-011610.3389/fpls.2025.16524781652478Research on time series prediction model for multi-factor environmental parameters in facilities based on LSTM-AT-DP modelLongwei Liang0Longwei Liang1Hui Shi2Hui Shi3Zhaoyuan Wang4Shengjie Wang5Changhong Li6Ming Diao7College of Agriculture, Shihezi University, Shihezi, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaInternational PhD School, University of Almería, Almería, SpainCollege of Agriculture, Shihezi University, Shihezi, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi, ChinaCollege of Agriculture, Shihezi University, Shihezi, ChinaCollege of Agriculture, Shihezi University, Shihezi, ChinaIntroductionExisting facility environment prediction models often suffer from low accuracy, poor timeliness, and error accumulation in long-term predictions under multifactor nonlinear coupling conditions. These limitations significantly constrain the effectiveness of precise environmental regulation in agricultural facilities.MethodsTo address these challenges, this paper proposes a novel facility environment prediction model (LSTM-AT-DP) integrating Long Short-Term Memory networks with attention mechanisms and advanced data preprocessing. The model architecture employs: (1) a Data Preprocessing (DP) module combining Wavelet Threshold Denoising (WTD) for noise elimination and Sliding Window (SW) technique for feature matrix construction; (2) an LSTM core for deep temporal modeling; and (3) an Attention Mechanism (AT) for dynamic feature weighting to enhance critical temporal feature extraction.ResultsIn 24-hour prediction tests, the model achieved determination coefficients (R²) of 0.9602 (temperature), 0.9529 (humidity), and 0.9839 (radiation), representing improvements of 3.89%, 5.53%, and 2.84% respectively over baseline LSTM models. Corresponding RMSE reductions were 0.6830, 1.8759, and 12.952 for these parameters.DiscussionThe results demonstrate that the LSTM-AT-DP model significantly enhances prediction accuracy while effectively suppressing error accumulation in long-term forecasts. This advancement provides robust technical support for precise facility environment regulation, with particular improvements observed in humidity prediction. The integrated attention mechanism proves particularly effective in identifying and weighting critical temporal features across all measured environmental parameters.https://www.frontiersin.org/articles/10.3389/fpls.2025.1652478/fullLSTMattention mechanismwavelet threshold denoisingmulti-factor time series forecastingenvironmental prediction
spellingShingle Longwei Liang
Longwei Liang
Hui Shi
Hui Shi
Zhaoyuan Wang
Shengjie Wang
Changhong Li
Ming Diao
Research on time series prediction model for multi-factor environmental parameters in facilities based on LSTM-AT-DP model
Frontiers in Plant Science
LSTM
attention mechanism
wavelet threshold denoising
multi-factor time series forecasting
environmental prediction
title Research on time series prediction model for multi-factor environmental parameters in facilities based on LSTM-AT-DP model
title_full Research on time series prediction model for multi-factor environmental parameters in facilities based on LSTM-AT-DP model
title_fullStr Research on time series prediction model for multi-factor environmental parameters in facilities based on LSTM-AT-DP model
title_full_unstemmed Research on time series prediction model for multi-factor environmental parameters in facilities based on LSTM-AT-DP model
title_short Research on time series prediction model for multi-factor environmental parameters in facilities based on LSTM-AT-DP model
title_sort research on time series prediction model for multi factor environmental parameters in facilities based on lstm at dp model
topic LSTM
attention mechanism
wavelet threshold denoising
multi-factor time series forecasting
environmental prediction
url https://www.frontiersin.org/articles/10.3389/fpls.2025.1652478/full
work_keys_str_mv AT longweiliang researchontimeseriespredictionmodelformultifactorenvironmentalparametersinfacilitiesbasedonlstmatdpmodel
AT longweiliang researchontimeseriespredictionmodelformultifactorenvironmentalparametersinfacilitiesbasedonlstmatdpmodel
AT huishi researchontimeseriespredictionmodelformultifactorenvironmentalparametersinfacilitiesbasedonlstmatdpmodel
AT huishi researchontimeseriespredictionmodelformultifactorenvironmentalparametersinfacilitiesbasedonlstmatdpmodel
AT zhaoyuanwang researchontimeseriespredictionmodelformultifactorenvironmentalparametersinfacilitiesbasedonlstmatdpmodel
AT shengjiewang researchontimeseriespredictionmodelformultifactorenvironmentalparametersinfacilitiesbasedonlstmatdpmodel
AT changhongli researchontimeseriespredictionmodelformultifactorenvironmentalparametersinfacilitiesbasedonlstmatdpmodel
AT mingdiao researchontimeseriespredictionmodelformultifactorenvironmentalparametersinfacilitiesbasedonlstmatdpmodel